Approximation Bounds for Inference using Cooperative Cuts
Approximation Bounds for Inference using Cooperative Cuts
复制标题
使用合作切割进行推理的近似界限
DOI:
--
复制
发表时间:
2011
期刊:
影响因子:
--
通讯作者:
J. Bilmes
中科院分区:
文献类型:
--
作者:
S. Jegelka;J. Bilmes
We analyze a family of probability distributions that are characterized by an embedded combinatorial structure. This family includes models having arbitrary treewidth and arbitrary sized factors. Unlike general models with such freedom, where the "most probable explanation" (MPE) problem is inapproximable, the combinatorial structure within our model, in particular the indirect use of sub-modularity, leads to several MPE algorithms that all have approximation guarantees.